发明名称 |
Audio signal feature extraction |
摘要 |
The present invention provides a feature quantity extracting apparatus capable of more clearly distinguishing one audio signal from another audio signal. A frequency transforming section (11) performs a frequency transform on a signal portion corresponding to a prescribed time length, which is contained in an inputted audio signal, thereby deriving a frequency spectrum from the signal portion. A band extracting section (12) extracts a plurality of frequency bands from the frequency spectrum derived by the frequency transforming section (11), and outputs band spectra which are respective frequency spectra of the extracted frequency bands. A feature quantity calculating section (13) calculates respective prescribed feature quantities of the band spectra, and obtains each of the calculated prescribed feature quantities as a feature quantity of the audio signal. <IMAGE> |
申请公布号 |
EP1403783(A3) |
申请公布日期 |
2005.01.19 |
申请号 |
EP20030021363 |
申请日期 |
2003.09.22 |
申请人 |
MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD. |
发明人 |
MOCHINAGA, KAZUHIRO;OGAWA, TOMOKI;MORI, YOSHIHIRO |
分类号 |
G10L25/48;G11B27/032;G11B27/034;G11B27/036;G11B27/10;G11B27/11;G11B27/28;H04N5/781;H04N5/782;H04N5/85;H04N5/907;(IPC1-7):G10L11/00;G06F17/30 |
主分类号 |
G10L25/48 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|